# Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding

## TL;DR

This paper introduces a re-ranking method for dialogue responses that leverages event causality and role factored tensor embeddings to improve response coherence and diversity.

## Contribution

It presents a novel re-ranking approach using event causality relations and a role factored tensor model for better response selection in dialogue systems.

## Key findings

- Improved response coherence and diversity in dialogue systems.
- Effective use of event causality relations for response re-ranking.
- Robust matching of event causality with role factored tensor embeddings.

## Abstract

We propose a novel method for selecting coherent and diverse responses for a given dialogue context. The proposed method re-ranks response candidates generated from conversational models by using event causality relations between events in a dialogue history and response candidates (e.g., ``be stressed out'' precedes ``relieve stress''). We use distributed event representation based on the Role Factored Tensor Model for a robust matching of event causality relations due to limited event causality knowledge of the system. Experimental results showed that the proposed method improved coherency and dialogue continuity of system responses.